COROS Official MCP

This article tracks ongoing updates to the COROS MCP — the integration that connects your COROS account to AI tools like ChatGPT and Claude. Each release adds new data types you can query, expands what your AI can see, and improves reliability. If you're new here, scroll down for setup instructions. If you're already connected, check below to see what's new.

Update Log

June 22, 2026

Workout Data

• Query split-by-split workout data (lap/segment breakdowns per activity)
• Query workout feedback and notes logged by the athlete
• Retrieve .fit files for any workout record, including full GPS tracks and second-by-second data — capped at 50 file requests per calendar day
• Fixed issues causing incomplete or missing workout summary data

Health & Recovery Data

• Query menstrual cycle data
• Query time-series stress data
• Query time-series data from quick health checks
• Query time-series HRV data recorded during sleep

General

• Fixed several additional known bugs

May 19, 2026

• All regional URLs consolidated into a single endpoint: https://mcp.coros.com/mcp

May 9, 2026

• Supports connecting to COROS MCP via Skill (npm install -g coros-mcp)

May 5, 2026

• Query workout records and summary data
• Query fitness metrics: VO2max, running power, threshold pace, race prediction
• Query weekly training load, training volume assessment, and recovery status
• Query training schedule
• Query daily steps, calories, workout duration, and weekly load
• Query daily sleep data
• Query daily average heart rate, HRV, stress, and resting heart rate
• Query user profile and bound device information

What is this?

An MCP is a standardized "plug" that allows an AI model to securely connect with your local files, databases, and third-party tools so it can understand your specific data and perform tasks directly within those systems. This MCP tool for COROS allows you to ask simple questions like you would ask AI or search on Google, but it will allow the AI to directly access your training history:

For example:

"How did my running look this month?"

"I have a race in 6 weeks, am I ready?"

The AI reads your COROS data and answers you.

What you'll need before you start

• A COROS account (you have one if you use the COROS app)
• A subscription to ChatGPT Plus or Claude Pro. MCP features require a paid plan on most platforms.

Step 1 : Find your region's link

Copy the link that matches where you live:

Step 2 : Connect it to your AI tool

ChatGPT

1. Open ChatGPT → Settings → Apps → Advanced Settings
2. Turn on Developer Mode
3. Click Add App
4. Paste the link from Step 1
5. Authorize and log into your COROS account
6. Done — go ask it something

Claude (Desktop app)

1. Open Claude → click the gear icon (Settings)
2. Go to Connectors → Add Custom Connector
3. Paste the link from Step 1
4. Log into your COROS account when prompted
5. Configure the connector to allow your data to flow through
6. Click Save
7. Done — go ask it something

Note: the interface may look slightly different depending on your region or plan.

Step 3 : Try it

Go back to your AI chat and try typing:

"Show me my workouts from the past two weeks"

If it responds with your data, you're all set.

Troubleshooting

It says "connection failed"→ Double-check you copied the right link for your region (see Step 1)

It asks you to log in but nothing happens→ Make sure your COROS account works at coros.com first

You don't see "MCP Servers" in settings→ You likely need a Plus/PRO subscription for this feature on your platform. Free plans often don't support MCP.

Which platforms support MCP?→ ChatGPT, Claude, and Cursor all support it. The steps are similar — look for Settings → Extensions → MCP in whichever tool you use.

What about Gemini? Gemini doesn't currently support custom MCP connectors through the standard chat interface (gemini.google.com) the way ChatGPT and Claude do. With those two, it's a simple paste-the-URL, authorize, and go — Gemini's consumer app doesn't have that yet.

If you're comfortable working in a terminal, you can still connect via the Gemini CLI. Follow Google's setup guide here and use your region's COROS MCP link from Step 1 as the server URL. We'll update this guide if and when Google adds MCP connector support to the Gemini chat app.

Privacy and Data Disclaimer

This integration does not create any new security or privacy risks beyond those that already exist when using your COROS account and your chosen AI platform separately. It is a structured connection layer that allows the two systems to communicate in a controlled, permission-based way. The same standards of account security, data protection, and platform privacy continue to apply.

Your COROS data remains governed by COROS privacy and security protections, and your AI interactions remain governed by the policies, permissions, and settings of the AI platform you choose to use. In other words, connecting through MCP does not change the underlying rules around how your data is protected — it simply allows approved data and actions to move between systems in a more useful and efficient way.

Access is only granted through explicit user authorization. You decide whether to connect your account, and the connection only operates within the permissions you approve. Depending on the capabilities enabled, that may include both read access to analyze training data and write access for supported actions within the connected experience. Those permissions are not open-ended; they are limited to the scope of the integration and the controls provided by COROS and the AI platform.

Importantly, this integration is not a backdoor into your account, and it does not bypass existing authentication, privacy controls, or security safeguards. It uses the same identity, authorization, and protection principles that already apply across secure connected services.

In practical terms, users should think of this as a secure extension of the tools they already use: your data protections remain in place, your permissions still matter, and you remain in control of what is connected and what actions are allowed.